@inproceedings{cho-etal-2020-open,
title = "Open {K}orean Corpora: A Practical Report",
author = "Cho, Won Ik and
Moon, Sangwhan and
Song, Youngsook",
editor = "Park, Eunjeong L. and
Hagiwara, Masato and
Milajevs, Dmitrijs and
Liu, Nelson F. and
Chauhan, Geeticka and
Tan, Liling",
booktitle = "Proceedings of Second Workshop for NLP Open Source Software (NLP-OSS)",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.nlposs-1.12",
doi = "10.18653/v1/2020.nlposs-1.12",
pages = "85--93",
abstract = "Korean is often referred to as a low-resource language in the research community. While this claim is partially true, it is also because the availability of resources is inadequately advertised and curated. This work curates and reviews a list of Korean corpora, first describing institution-level resource development, then further iterate through a list of current open datasets for different types of tasks. We then propose a direction on how open-source dataset construction and releases should be done for less-resourced languages to promote research.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cho-etal-2020-open">
<titleInfo>
<title>Open Korean Corpora: A Practical Report</title>
</titleInfo>
<name type="personal">
<namePart type="given">Won</namePart>
<namePart type="given">Ik</namePart>
<namePart type="family">Cho</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sangwhan</namePart>
<namePart type="family">Moon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Youngsook</namePart>
<namePart type="family">Song</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of Second Workshop for NLP Open Source Software (NLP-OSS)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Eunjeong</namePart>
<namePart type="given">L</namePart>
<namePart type="family">Park</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Masato</namePart>
<namePart type="family">Hagiwara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dmitrijs</namePart>
<namePart type="family">Milajevs</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nelson</namePart>
<namePart type="given">F</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Geeticka</namePart>
<namePart type="family">Chauhan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liling</namePart>
<namePart type="family">Tan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Korean is often referred to as a low-resource language in the research community. While this claim is partially true, it is also because the availability of resources is inadequately advertised and curated. This work curates and reviews a list of Korean corpora, first describing institution-level resource development, then further iterate through a list of current open datasets for different types of tasks. We then propose a direction on how open-source dataset construction and releases should be done for less-resourced languages to promote research.</abstract>
<identifier type="citekey">cho-etal-2020-open</identifier>
<identifier type="doi">10.18653/v1/2020.nlposs-1.12</identifier>
<location>
<url>https://aclanthology.org/2020.nlposs-1.12</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>85</start>
<end>93</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Open Korean Corpora: A Practical Report
%A Cho, Won Ik
%A Moon, Sangwhan
%A Song, Youngsook
%Y Park, Eunjeong L.
%Y Hagiwara, Masato
%Y Milajevs, Dmitrijs
%Y Liu, Nelson F.
%Y Chauhan, Geeticka
%Y Tan, Liling
%S Proceedings of Second Workshop for NLP Open Source Software (NLP-OSS)
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F cho-etal-2020-open
%X Korean is often referred to as a low-resource language in the research community. While this claim is partially true, it is also because the availability of resources is inadequately advertised and curated. This work curates and reviews a list of Korean corpora, first describing institution-level resource development, then further iterate through a list of current open datasets for different types of tasks. We then propose a direction on how open-source dataset construction and releases should be done for less-resourced languages to promote research.
%R 10.18653/v1/2020.nlposs-1.12
%U https://aclanthology.org/2020.nlposs-1.12
%U https://doi.org/10.18653/v1/2020.nlposs-1.12
%P 85-93
Markdown (Informal)
[Open Korean Corpora: A Practical Report](https://aclanthology.org/2020.nlposs-1.12) (Cho et al., NLPOSS 2020)
ACL
- Won Ik Cho, Sangwhan Moon, and Youngsook Song. 2020. Open Korean Corpora: A Practical Report. In Proceedings of Second Workshop for NLP Open Source Software (NLP-OSS), pages 85–93, Online. Association for Computational Linguistics.